Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair
Loc2Repair:评估文件级问题定位在仓库级LLM修复中影响的框架
机构 * ITMO University(ITMO大学)
AI总结 提出Loc2Repair模块化评估框架,通过解耦定位与修复,在SWE-bench Verified上验证文件级定位能一致提升修复率(44.7%→49.1%)并降低平均耗时。
Comments To appear in the Proceedings of the Generative Code Intelligence Workshop (GeCoIn 2026), co-located with the 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026), Bremen, Germany, August 15--17, 2026